langchain[minor]: Updated DocugamiLoader, includes breaking changes (#…

…13265)

There are the following main changes in this PR:

1. Rewrite of the DocugamiLoader to not do any XML parsing of the DGML
format internally, and instead use the `dgml-utils` library we are
separately working on. This is a very lightweight dependency.
2. Added MMR search type as an option to multi-vector retriever, similar
to other retrievers. MMR is especially useful when using Docugami for
RAG since we deal with large sets of documents within which a few might
be duplicates and straight similarity based search doesn't give great
results in many cases.

We are @docugami on twitter, and I am @tjaffri

---------

Co-authored-by: Taqi Jaffri <[email protected]>

docs/docs/integrations/providers/docugami.mdx

@@ -8,7 +8,7 @@
 
 
 ```bash
-pip install lxml
+pip install dgml-utils
 ```
 
 ## Document Loader

docs/docs/modules/data_connection/retrievers/multi_vector.ipynb

@@ -143,7 +143,7 @@
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '10e9cbc0-4ba5-4d79-a09b-c033d1ba7b01', 'source': '../../state_of_the_union.txt'})"
+       "Document(page_content='Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '455205f7-bb7d-4c36-b442-d1d6f9f701ed', 'source': '../../state_of_the_union.txt'})"
       ]
      },
      "execution_count": 8,
@@ -165,7 +165,7 @@
     {
      "data": {
       "text/plain": [
-       "9874"
+       "9875"
       ]
      },
      "execution_count": 9,
@@ -178,6 +178,39 @@
     "len(retriever.get_relevant_documents(\"justice breyer\")[0].page_content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "cdef8339-f9fa-4b3b-955f-ad9dbdf2734f",
+   "metadata": {},
+   "source": [
+    "The default search type the retriever performs on the vector database is a similarity search. LangChain Vector Stores also support searching via [Max Marginal Relevance](https://api.python.langchain.com/en/latest/schema/langchain.schema.vectorstore.VectorStore.html#langchain.schema.vectorstore.VectorStore.max_marginal_relevance_search) so if you want this instead you can just set the `search_type` property as follows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "36739460-a737-4a8e-b70f-50bf8c8eaae7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9875"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.retrievers.multi_vector import SearchType\n",
+    "\n",
+    "retriever.search_type = SearchType.mmr\n",
+    "\n",
+    "len(retriever.get_relevant_documents(\"justice breyer\")[0].page_content)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "d6a7ae0d",
@@ -576,7 +609,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,